CN104952754A - Coated silicon chip sorting method based on machine vision - Google Patents
Coated silicon chip sorting method based on machine vision Download PDFInfo
- Publication number
- CN104952754A CN104952754A CN201510224553.XA CN201510224553A CN104952754A CN 104952754 A CN104952754 A CN 104952754A CN 201510224553 A CN201510224553 A CN 201510224553A CN 104952754 A CN104952754 A CN 104952754A
- Authority
- CN
- China
- Prior art keywords
- silicon chip
- image
- plated film
- information
- edge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
- H01L21/67005—Apparatus not specifically provided for elsewhere
- H01L21/67242—Apparatus for monitoring, sorting or marking
- H01L21/67271—Sorting devices
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
- H01L22/20—Sequence of activities consisting of a plurality of measurements, corrections, marking or sorting steps
- H01L22/24—Optical enhancement of defects or not directly visible states, e.g. selective electrolytic deposition, bubbles in liquids, light emission, colour change
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of machine vision sorting and discloses a coated silicon chip sorting method based on machine vision. The method includes: processing and analyzing acquired images by means of technologies of color image coordinate transformation, color image segmentation, color image RGB (red green blue) spatial analysis, image processing, big data logic statistical analysis and processing and the like; extracting image color information; subjecting the information to image binaryzation, filtering for screening and conversion; executing useful information according to an algorithm based on sample big data logic statistical analysis and processing to sort coated silicon chips into unqualified chips, uniform red chips and qualified chips. By means of quick acquisition of information of color images on surfaces of the coated silicon chips, real-time online silicon chip flaw recognition and sorting can be realized stably, efficiently and accurately, and test results are displayed in real time; in addition, by communication between data acquisition equipment and a manipulator, quickness in adoption of different mechanical actions corresponding to different types can be realized.
Description
Technical field
The invention belongs to machine vision sorter technical field, be specifically related to silicon chip method for separating after the plated film based on machine vision.
Background technology
Silicon chip is the primary raw material of manufacture of solar cells, the quality of its coating quality directly determines the quality of cell piece printing in subsequent handling, thus affect the performance of solar cell, therefore must carry out sorting to silicon chip after plated film, the defective silicon chip of existing defects is rejected.But due to the impact of the factors such as the temperature of each groove of graphite boat is different, external environment, after plated film silicon chip there will be jaundice sheet, rubescent, the sheet that turns white, fragment, surface blot etc. defective or evenly red, the diversity of these silicon chip kinds and complexity cause the uncertainty to its detection method.
A lot of solar battery sheet manufacturer is main still based on manual detection at present, and this also brings, and examination criteria is uncertain, efficiency is low, fragment is many, high in cost of production problem, so be difficult to reach industrial standard and requirement.
Summary of the invention
Goal of the invention: the object of the present invention is to provide a kind of based on silicon chip method for separating after the plated film of machine vision, its have stability high, with silicon chip is contactless, speed is fast etc. advantage, can real-time online, quick and precisely, detect defect and the classification of silicon chip after plated film efficiently and stably, automatically sorting is carried out to silicon chip, and automatically substandard product is taken out, put into and specify silicon box.
Technical scheme: for achieving the above object, the present invention adopts following technical scheme:
Based on silicon chip method for separating after the plated film of machine vision, comprise the steps:
Step 201, Received signal strength, gather image, it comprises:
Step 2011, after plated film, silicon chip arrives sensing station, and transducer sends analog signal to data acquisition equipment, is converted to digital signal transfers to system via capture card;
Step 2012, after system acceptance to collection signal, triggers camera, gathers image, and by silicon chip colored images' transmission after the plated film of collection to graphics processing unit;
Step 202, carry out coordinate transform and Iamge Segmentation to the coloured image of silicon chip after plated film, it comprises:
Step 2021, carries out coordinate transform to the coloured image of silicon chip after plated film, adopts automatically to search edge algorithms and find out silicon chip after plated film, obtains its angle information; Its method first determines a region of search, in region of search, arranges some scounting lines from top to bottom, search the transition point of pixel, afterwards the transition point on all scounting lines is fitted to straight line, obtain the angle information of gained straight line; Its angle information is:
angle
1=θ (1)
Then utilize formula (2), by image rotation, carry out coordinate transform, for Iamge Segmentation is prepared;
angle=360-θ (2)
Step 2022, automatically searching image border algorithm carries out edge finding to the four edges of silicon chip after plated film respectively in real time in employing; Obtain the coordinate information of respective edge line; Its coordinate information is:
lineleft:(x
11,y
11),(x
12,y
12) (3)
lineright:(x
21,y
21),(x
22,y
22) (4)
linetop:(x
31,y
31),(x
32,y
32) (5)
linebottom:(x
41,y
41),(x
42,y
42) (6)
Wherein lineleft, lineright, linetop, linebottom are respectively two apex coordinates of obtained four edges edge line segment (left and right, upper and lower);
Step 2023, respectively based on two apex coordinates of formula (3), (4), (5), (6) gained, according to trying to achieve four edges edge straight line Yl (left hand edge), Yr (right hand edge), Yt (top edge), Yb (lower limb) shown in formula (7);
y=ax+b (7)
Based on obtained four edges edge linear equation, ask for intersection point m, n of Yl and Yt, Yr and Yb successively; With the starting point and ending point that a m and some n are segmentation image, obtain silicon chip and background separation this volume image out after plated film;
Step 203, with coloured image rgb space for silicon chip image after above-mentioned obtained plated film is divided into R, G, B tri-planes by carrier, obtain the gray value information of three planes respectively;
Step 204, the B plane binaryzation obtained above-mentioned steps 203, adopt median filter to carry out filtering and noise reduction process to gained binary image, makes image under the condition ensureing original information, reduce the interference of noise effect and external environment to greatest extent;
Step 205, carry out information gathering to the binary image after obtained filtering process, obtaining its pixel and information, judge whether silicon chip is fragment according to these data, is that fragment is then classified as a defective class;
Step 206, respectively half-tone information collection is carried out to silicon chip R, G, B plane after obtained complete plated film, obtain pixel value be 0 frequency values and whole image pixel and ratio;
Step 207, the ratio that above-mentioned steps obtained carry out a series of comparison and judgement with the logical relation obtained by the large Data Management Analysis of sample, obtain the separation results of silicon chip after plated film.
In step 207, after described plated film, the separation results of silicon chip is divided into defective, qualified, even red three classes; When being divided into defective class, will mechanical arm be sent a signal to, and being sucked and specifying defective silicon box; When be divided into evenly red class time, will mechanical arm be sent a signal to, and be sucked and specify even red silicon box; When being divided into qualified class, any signal will not being sent to mechanical arm, and allowing it flow directly into the gaily decorated basket.
Inventive principle: the object of sorting of the present invention is through the silicon chip after graphite boat plated film, its sorting schemes have employed color Image Segmentation, coloured image rgb space analytical technology, image processing techniques, large mathematical logic statistical analysis and treatment technology etc. process silicon chip image after the plated film of Real-time Collection and analyze, and silicon chip after plated film is divided into defective, evenly red and qualified three classes.Wherein, in step 207, the large data processing of sample and statistical analysis are the analysis of image information separately of R, G, B tri-planes of collecting according to step described above based on a large amount of entity sample, conclusion and checking.
Beneficial effect: compared with prior art, of the present invention based on silicon chip method for separating after the plated film of machine vision, by the color image information of silicon chip surface after Quick Acquisition plated film, Defect identification accurately and sorting can be carried out real-time online stability and high efficiency, and show testing result in real time, automatically sorting classification is divided into even redness, defective item and qualified product three class, also by data acquisition equipment and manipulator communication, makes the different classification of its correspondence take different mechanical actions fast.
Accompanying drawing explanation
Fig. 1 is silicon chip grouping system flow chart after plated film;
Fig. 2 is that silicon chip arrives sensing station end view;
Fig. 3 be after plated film silicon chip in step 2021, search edge after result images;
Fig. 4 is the contrast images of silicon chip in step 2021 before and after coordinate transform after plated film;
Fig. 5 is silicon chip edge lookup result image after plated film in step 2023;
Fig. 6 is the result images of silicon chip and background separation after plated film in step 2023.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described further.
As shown in Figure 1, based on the method for separating of silicon chip after the plated film of machine vision, comprise the steps:
Step 201, Received signal strength, gather image, it comprises:
Step 2011, after plated film, silicon chip arrives sensing station, as shown in Figure 2, white background plate 1, photoelectric sensor 2, silicon chip 3 after plated film; Transducer sends analog signal to data acquisition equipment, is converted to digital signal transfers to system via capture card;
Step 2012, after system acceptance to collection signal, triggers camera, gathers image, and by silicon chip colored images' transmission after the plated film of collection to graphics processing unit;
Step 202, carry out coordinate transform and Iamge Segmentation to the coloured image of silicon chip after plated film, it comprises:
Step 2021, carries out coordinate transform to the coloured image of silicon chip after plated film, adopts automatically to search edge algorithms and find out silicon chip after plated film, obtains its angle information; Its method first determines a region of search, in region of search, some scounting lines are set from top to bottom, search the transition point of pixel, afterwards the transition point on all scounting lines is fitted to straight line 4, as shown in Figure 3, obtain the angle information of gained straight line 4, straight line 4 is by the straight line of pixel transition point matching; Its angle information is:
angle
1=θ (1)
Then utilize formula (2), by image rotation, carry out coordinate transform, as shown in Figure 4, the left-side images of Fig. 4 is the situation before coordinate transform, and the image right of Fig. 4 is the situation after coordinate transform, for Iamge Segmentation is prepared;
angle=360-θ (2)
Step 2022, automatically searching image border algorithm carries out edge finding to the four edges of silicon chip after plated film respectively in real time in employing; Obtain the coordinate information of respective edge line; Its coordinate information is:
lineleft:(x
11,y
11),(x
12,y
12) (3)
lineright:(x
21,y
21),(x
22,y
22) (4)
linetop:(x
31,y
31),(x
32,y
32) (5)
linebottom:(x
41,y
41),(x
42,y
42) (6)
Wherein lineleft, lineright, linetop, linebottom are respectively two apex coordinates of obtained four edges edge line segment (left and right, upper and lower);
Step 2023, respectively based on two apex coordinates of formula (3), (4), (5), (6) gained, according to trying to achieve four edges edge straight line Yl (left hand edge), Yr (right hand edge), Yt (top edge), Yb (lower limb) shown in formula (7), as shown in Figure 5;
y=ax+b (7)
Based on obtained four edges edge linear equation, ask for intersection point m, n of Yl and Yt, Yr and Yb successively; With a m and some n for splitting the starting point and ending point of image, obtain silicon chip and background separation this volume image out after plated film, as shown in Figure 6, the left-side images of Fig. 6 is silicon chip image after the plated film comprising background, on the right side of Fig. 6 for remove background plated film after this volume image of silicon chip.
Step 203, with coloured image rgb space for silicon chip image after above-mentioned obtained plated film is divided into R, G, B tri-planes by carrier, obtain the gray value information of three planes respectively;
Step 204, the B plane binaryzation obtained above-mentioned steps 203, adopt median filter to carry out filtering and noise reduction process to gained binary image, makes image reduce noise effect to greatest extent under the condition ensureing original information;
Step 205, carry out information gathering to the binary image after obtained filtering process, obtaining its pixel and information, judge whether silicon chip is fragment according to these data, is that fragment is then classified as a defective class;
Step 206, respectively half-tone information collection is carried out to silicon chip R, G, B plane after obtained complete plated film, obtain pixel value be 0 frequency values and whole image pixel and ratio; In each plane of R, G, B pixel value be 0 place represent that this region is black, its field color corresponding in coloured image is darker;
Step 207, the ratio that above-mentioned steps obtained are compared with the logical relation obtained by the large data processing of sample and statistical analysis and judge, obtain the separation results of silicon chip after plated film, and after plated film, silicon chip is divided into defective, qualified, even red three classes; When being divided into defective class, will mechanical arm be sent a signal to, and being sucked and specifying defective silicon box; When be divided into evenly red class time, will mechanical arm be sent a signal to, and be sucked and specify even red silicon box; When being divided into qualified class, any signal will not being sent to mechanical arm, and allowing it flow directly into the gaily decorated basket.
Through above seven steps, avoid manually to the uncertainty that Defect after plated film detects and classifies, significantly reduce the fragment rate that the sorting of human contact's formula causes, meet the operating efficiency of online production, on-line checkingi, online sorting simultaneously, and fast, stable, easy to operate.
Claims (2)
1., based on silicon chip method for separating after the plated film of machine vision, it is characterized in that, comprise the steps:
Step 201, Received signal strength, gather image, it comprises:
Step 2011, after plated film, silicon chip arrives sensing station, and transducer sends analog signal to data acquisition equipment, is converted to digital signal transfers to system via capture card;
Step 2012, after system acceptance to collection signal, triggers camera, gathers image, and by silicon chip colored images' transmission after the plated film of collection to graphics processing unit;
Step 202, carry out coordinate transform and Iamge Segmentation to the coloured image of silicon chip after plated film, it comprises:
Step 2021, carries out coordinate transform to the coloured image of silicon chip after plated film, adopts automatically to search edge algorithms and find out silicon chip after plated film, obtains its angle information; Its method first determines a region of search, in region of search, arranges some scounting lines from top to bottom, search the transition point of pixel, afterwards the transition point on all scounting lines is fitted to straight line, obtain the angle information of gained straight line; Its angle information is:
angle
1=θ (1)
Then utilize formula (2), by image rotation, carry out coordinate transform, for Iamge Segmentation is prepared;
angle=360-θ (2)
Step 2022, automatically searching image border algorithm carries out edge finding to the four edges of silicon chip after plated film respectively in real time in employing; Obtain the coordinate information of respective edge line; Its coordinate information is:
lineleft:(x
11,y
11),(x
12,y
12) (3)
lineright:(x
21,y
21),(x
22,y
22) (4)
linetop:(x
31,y
31),(x
32,y
32) (5)
linebottom:(x
41,y
41),(x
42,y
42) (6)
Wherein lineleft, lineright, linetop, linebottom are respectively two apex coordinates of obtained four edges edge line segment (left and right, upper and lower);
Step 2023, respectively based on two apex coordinates of formula (3), (4), (5), (6) gained, according to trying to achieve four edges edge straight line Yl (left hand edge), Yr (right hand edge), Yt (top edge), Yb (lower limb) shown in formula (7);
y=ax+b (7)
Based on obtained four edges edge linear equation, ask for intersection point m, n of Yl and Yt, Yr and Yb successively; With the starting point and ending point that a m and some n are segmentation image, obtain silicon chip and background separation this volume image out after plated film;
Step 203, with coloured image rgb space for silicon chip image after above-mentioned obtained plated film is divided into R, G, B tri-planes by carrier, obtain the gray value information of three planes respectively;
Step 204, the B plane binaryzation obtained above-mentioned steps 203, adopt median filter to carry out filtering and noise reduction process to gained binary image, makes image under the condition ensureing original information, reduce the interference of noise effect and external environment to greatest extent;
Step 205, carry out information gathering to the binary image after obtained filtering process, obtaining its pixel and information, judge whether silicon chip is fragment according to these data, is that fragment is then classified as a defective class;
Step 206, respectively half-tone information collection is carried out to silicon chip R, G, B plane after obtained complete plated film, obtain pixel value be 0 frequency values and whole image pixel and ratio;
Step 207, the ratio that above-mentioned steps obtained carry out a series of comparison and judgement with the logical relation obtained by the large Data Management Analysis of sample, obtain the separation results of silicon chip after plated film.
2. according to claim 1ly it is characterized in that: in step 207 based on silicon chip method for separating after the plated film of machine vision, after described plated film, the separation results of silicon chip is divided into defective, qualified, even red three classes; When being divided into defective class, will mechanical arm be sent a signal to, and being sucked and specifying defective silicon box; When be divided into evenly red class time, will mechanical arm be sent a signal to, and be sucked and specify even red silicon box; When being divided into qualified class, any signal will not being sent to mechanical arm, and allowing it flow directly into the gaily decorated basket.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510224553.XA CN104952754B (en) | 2015-05-05 | 2015-05-05 | Silicon chip method for separating after plated film based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510224553.XA CN104952754B (en) | 2015-05-05 | 2015-05-05 | Silicon chip method for separating after plated film based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104952754A true CN104952754A (en) | 2015-09-30 |
CN104952754B CN104952754B (en) | 2017-08-01 |
Family
ID=54167321
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510224553.XA Expired - Fee Related CN104952754B (en) | 2015-05-05 | 2015-05-05 | Silicon chip method for separating after plated film based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104952754B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105388162A (en) * | 2015-10-28 | 2016-03-09 | 镇江苏仪德科技有限公司 | Raw material silicon wafer surface scratch detection method based on machine vision |
CN106814088A (en) * | 2016-12-30 | 2017-06-09 | 镇江苏仪德科技有限公司 | Based on machine vision to the detection means and method of cell piece colour sorting |
CN106841211A (en) * | 2016-12-30 | 2017-06-13 | 镇江苏仪德科技有限公司 | Platform and method of a kind of utilization machine vision to cell piece surface defects detection |
CN111129216A (en) * | 2019-12-17 | 2020-05-08 | 湖南红太阳光电科技有限公司 | Equipment for preparing double-sided passivation film of PERC battery and using method thereof |
CN111159253A (en) * | 2019-12-28 | 2020-05-15 | 重庆友辉建筑科技有限公司 | Big data statistical system of light steel villa part |
CN111628045A (en) * | 2020-05-28 | 2020-09-04 | 湖南红太阳光电科技有限公司 | Feeding and discharging method for PECVD surface coating based on coating detection |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060210142A1 (en) * | 2005-01-26 | 2006-09-21 | Semiconductor Energy Laboratory Co., Ltd. | Pattern inspection method and apparatus |
JP2009105230A (en) * | 2007-10-23 | 2009-05-14 | Shibaura Mechatronics Corp | Device and method of inspecting disc substrate |
CN102974551A (en) * | 2012-11-26 | 2013-03-20 | 华南理工大学 | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy |
CN103752534A (en) * | 2014-01-14 | 2014-04-30 | 温州中波电气有限公司 | Intelligent-vision-based image intelligent recognizing-sorting device and method |
CN104240204A (en) * | 2014-09-11 | 2014-12-24 | 镇江苏仪德科技有限公司 | Solar silicon wafer and battery piece counting method based on image processing |
-
2015
- 2015-05-05 CN CN201510224553.XA patent/CN104952754B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060210142A1 (en) * | 2005-01-26 | 2006-09-21 | Semiconductor Energy Laboratory Co., Ltd. | Pattern inspection method and apparatus |
JP2009105230A (en) * | 2007-10-23 | 2009-05-14 | Shibaura Mechatronics Corp | Device and method of inspecting disc substrate |
CN102974551A (en) * | 2012-11-26 | 2013-03-20 | 华南理工大学 | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy |
CN103752534A (en) * | 2014-01-14 | 2014-04-30 | 温州中波电气有限公司 | Intelligent-vision-based image intelligent recognizing-sorting device and method |
CN104240204A (en) * | 2014-09-11 | 2014-12-24 | 镇江苏仪德科技有限公司 | Solar silicon wafer and battery piece counting method based on image processing |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105388162A (en) * | 2015-10-28 | 2016-03-09 | 镇江苏仪德科技有限公司 | Raw material silicon wafer surface scratch detection method based on machine vision |
CN105388162B (en) * | 2015-10-28 | 2017-12-01 | 镇江苏仪德科技有限公司 | Raw material silicon chip surface scratch detection method based on machine vision |
CN106814088A (en) * | 2016-12-30 | 2017-06-09 | 镇江苏仪德科技有限公司 | Based on machine vision to the detection means and method of cell piece colour sorting |
CN106841211A (en) * | 2016-12-30 | 2017-06-13 | 镇江苏仪德科技有限公司 | Platform and method of a kind of utilization machine vision to cell piece surface defects detection |
CN111129216A (en) * | 2019-12-17 | 2020-05-08 | 湖南红太阳光电科技有限公司 | Equipment for preparing double-sided passivation film of PERC battery and using method thereof |
CN111159253A (en) * | 2019-12-28 | 2020-05-15 | 重庆友辉建筑科技有限公司 | Big data statistical system of light steel villa part |
CN111628045A (en) * | 2020-05-28 | 2020-09-04 | 湖南红太阳光电科技有限公司 | Feeding and discharging method for PECVD surface coating based on coating detection |
CN111628045B (en) * | 2020-05-28 | 2021-12-24 | 湖南红太阳光电科技有限公司 | Feeding and discharging method for PECVD surface coating based on coating detection |
Also Published As
Publication number | Publication date |
---|---|
CN104952754B (en) | 2017-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104952754B (en) | Silicon chip method for separating after plated film based on machine vision | |
CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN106238350B (en) | A kind of solar battery sheet method for separating and system based on machine vision | |
CN105388162B (en) | Raw material silicon chip surface scratch detection method based on machine vision | |
CN111815564B (en) | Method and device for detecting silk ingots and silk ingot sorting system | |
CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
Ali et al. | Automated fruit grading system | |
CN102095731A (en) | System and method for recognizing different defect types in paper defect visual detection | |
CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
CN112184648A (en) | Piston surface defect detection method and system based on deep learning | |
CN112893159B (en) | Coal gangue sorting method based on image recognition | |
CN207238542U (en) | A kind of thin bamboo strip defect on-line detecting system based on machine vision | |
CN110434090A (en) | A kind of carrot surface flaw detecting method | |
CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
CN110108712A (en) | Multifunctional visual sense defect detecting system | |
CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
CN106645180A (en) | Method for checking defects of substrate glass, field terminal and server | |
CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
CN112560896A (en) | Fruit quality screening and classifying system based on image processing | |
CN202351182U (en) | Online high-speed detection system for defects on surface of tinplate | |
CN113706496B (en) | Aircraft structure crack detection method based on deep learning model | |
CN111028207A (en) | Button flaw detection method based on brain-like immediate-universal feature extraction network | |
CN110458231B (en) | Ceramic product detection method, device and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170801 Termination date: 20180505 |
|
CF01 | Termination of patent right due to non-payment of annual fee |